Syllable-Based Probabilistic Morphological Analysis Model of Korean

摘要

In this paper, we present a syllable-based probabilistic morphological analysis model of Korean. While the previous morphological analyzers that regard morpheme as a processing unit, the model exploits syllable as a processing unit in order to endure the unknown word problem. Actually, it does not use any morpheme dictionary. In contract to the previous systems that depend on manually constructed linguistic knowledge, the proposed system can fully automatically acquire the linguistic knowledge from annotated corpora. Besides, without any modification, the system can be applied to other corpus having a different tagset and annotation guidelines. We describe the model and present experimental results on two corpora.